Reação de genótipos de cafeeiro à Hemileia vastatrix e à Cercospora coffeicola

Coffee plants were introduced in Brazil in the Northern State of Para around 1727. Two major diseases have affected coffee trees in the country. One is rust, caused by fungus Hemileia vastatrix and accountable for production losses up to 50%. The other one is Cercospora leaf spot, caused by fungus Cercospora coffeicola endemic to all Brazilian coffee farms and, therefore, economically critical due to production losses both in the plant nursery and in the field. Availability of resistant varieties has been a constant challenge for breeders. Research programs play an important role in the search for new resistant and/or tolerant genotypes, since over time plants can become susceptible to new, genetically variable races of pathogens. This study aimed to evaluate the incidence and severity of such diseases, the resistance of different coffee genotypes to H. vastatrix and C. coffeicola pathogens, as well as the productivity of said genotypes in dense planting system. The experimental design consisted of randomized blocks, with twelve genotypes (treatments) and two replications (blocks). SISVAR® program was used to analyze data and compare them building on Scott-Knott test and Tukey’s test with a probability of 5%. Disease incidence and severity percentage were assessed for both Cercospora leaf spot and rust. Means were used to calculate the area under the disease progress curve (AUDPC) of both diseases. As to rust, the most resistant genotypes were H586-6, IBC 12, and H556-7 H567-6. As to Cercospora leaf spot and productivity, no statistical differences were found across genotypes. The dense planting system did not impair plant development, but favored disease evolution given the microclimate it produces.

Classificação de nódulos pulmonares em imagens tomográficas utilizando redes neurais artificiais em cascata

Lung cancer is the most common of malignant tumors, with 1.59 million new cases worldwide in 2012. Early detection is the main factor to determine the survival of patients affected by this disease. Furthermore, the correct classification is important to define the most appropriate therapeutic approach as well as suggest the prognosis and the clinical disease evolution. Among the exams used to detect lung cancer, computed tomography have been the most indicated. However, CT images are naturally complex and even experts medical are subject to fault detection or classification. In order to assist the detection of malignant tumors, computer-aided diagnosis systems have been developed to aid reduce the amount of false positives biopsies. In this work it was developed an automatic classification system of pulmonary nodules on CT images by using Artificial Neural Networks. Morphological, texture and intensity attributes were extracted from lung nodules cut tomographic images using elliptical regions of interest that they were subsequently segmented by Otsu method. These features were selected through statistical tests that compare populations (T test of Student and U test of Mann-Whitney); from which it originated a ranking. The features after selected, were inserted in Artificial Neural Networks (backpropagation) to compose two types of classification; one to classify nodules in malignant and benign (network 1); and another to classify two types of malignancies (network 2); featuring a cascade classifier. The best networks were associated and its performance was measured by the area under the ROC curve, where the network 1 and network 2 achieved performance equal to 0.901 and 0.892 respectively.